Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 31-LLAMASCOPE-RES-131K
    6. 44442
    Prev
    Next
    INDEX
    Explanations

    features related to user-friendly technology and convenience

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ernals
    -0.07
    agara
    -0.06
    æķ£
    -0.06
    outers
    -0.06
     errorThrown
    -0.06
    .Formatter
    -0.06
    /gpl
    -0.06
    asury
    -0.06
    .MixedReality
    -0.06
    opak
    -0.06
    POSITIVE LOGITS
     clicks
    0.17
     click
    0.17
     taps
    0.16
     tap
    0.15
     button
    0.14
     push
    0.14
     presses
    0.14
     touch
    0.14
     mouse
    0.14
     press
    0.13
    Activations Density 0.062%

    No Known Activations